방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 도메인 적응형 이미지 분류× | 미세 조정된 이미지 분류× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2015–2016 | 2010–2014 |
| 창시자≠ | Ganin, Y. & Lempitsky, V. (domain-adversarial formulation) | Yosinski, J. et al.; Pan, S. J. & Yang, Q. |
| 유형≠ | Domain adaptation / transfer learning | Transfer learning / fine-tuning |
| 원전≠ | Ganin, Y., Ustunova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59), 1–35. link ↗ | Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems (NeurIPS), 27, 3320–3328. link ↗ |
| 별칭 | domain adaptation for image classification, DAIC, cross-domain image classification, domain-shift-robust image recognition | fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier |
| 관련≠ | 3 | 5 |
| 요약≠ | Domain-adaptive image classification trains a visual classifier on a labeled source domain and adapts it to a target domain where labeled data are scarce or absent. By aligning feature distributions across domains, the model retains discriminative accuracy on the target distribution without requiring full target re-annotation, making it practical in real-world deployment scenarios where domain shift is unavoidable. | Fine-tuned image classification adapts a large neural network pretrained on a broad image corpus (such as ImageNet) to a specific target domain by continuing training on labeled domain images. This approach achieves strong accuracy with far fewer target-domain samples than training from scratch, making it the dominant paradigm for applied computer vision tasks. |
| ScholarGate데이터셋 ↗ |
|
|